UserGuide BioStat Prime Help

Linear Regression

Linear regression is one of the most widely used techniques in biostatistics. It is ideal when the relationship between one or more independent variables (predictors) and a dependent variable is assumed to be linear. BioStat Prime supports a variety of linear modeling methods, making it suitable for both beginners and advanced analysts working with health, clinical, and food science data. Linear regression assumes a straight-line (or planar, in multivariable contexts) relationship between the dependent variable and predictor(s). Ideal when responses change proportionally with variables.

Comprehensive Linear Regression Analysis Support in BioStat Prime

BioStat Prime offers a robust suite of regression techniques to handle a wide range of statistical modeling needs — from simple linear regression to advanced survival models. The following regression methods are supported:

  • Cox, Advanced

  • Cox, Basic

  • Cox, Binary Time-Dependent Covariates

  • Cox, Fine-Gray

  • Cox Regression, Multiple Models

  • Cox, Stratified

  • Linear, Advanced

  • Linear, Basic

  • Logistic, Advanced

  • Linear Regression, Multiple Models

  • Logistic, Basic

  • Multinomial Logit

  • Logistic, Conditional

  • Logistic Regression, Multiple Models

  • Ordinal

  • Quantile

  • Parametric Survival Regression

Last modified: 31 July 2025